memory-manager

Retrieve prior project context from MEMORY.md and persist new conventions to memory/.

87|20|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/openaeon/OpenAEON --skill memory-manager-openaeon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-manager
Source: https://github.com/openaeon/OpenAEON/tree/main/skills/memory-manager
Command: npx skills add https://github.com/openaeon/OpenAEON --skill memory-manager-openaeon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents repeating past decisions and missing project conventions by forcing you to research existing memory, apply it during work, and persist any new learnings.

Core Features & Use Cases

  • Memory-First Protocol: Enforces Research → Response/Execution → Learning for every task to keep outputs consistent with historical context.
  • Deterministic Context Retrieval: Uses memory_search and memory_get to pull relevant prior notes before writing or answering about past work.
  • Persistent Team Knowledge: Saves newly discovered conventions, architectural decisions, and user preferences back into the memory/ markdown store for future tasks.

Use Case: When implementing a new feature, you can reuse earlier architectural decisions and coding conventions already stored in MEMORY.md and memory/*.md, then automatically store any updated rules after the change.

Quick Start

Use the memory-manager skill to start any task by researching MEMORY.md and memory/*.md, then apply the retrieved conventions throughout the work and save new learnings at the end.

Frequently Asked Questions about memory-manager

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I persist project conventions and architectural decisions across agent sessions?

To persist project conventions across sessions, use a memory-first protocol that retrieves prior context from markdown notes before executing tasks and writes newly learned architectural decisions back into the memory directory for future reuse.

What is a memory-first research and execution workflow for software development?

A memory-first workflow enforces a Research, Response, and Learning cycle for software development, ensuring historical decisions and user preferences are retrieved from existing markdown files before answering and updated conventions are saved afterward.

How do I retrieve historical project context before implementing a new feature?

Retrieve historical project context by running memory search on MEMORY.md and markdown files in the memory directory, then use targeted memory get commands to pull relevant prior notes before writing or answering about past work.

Can I use markdown files to store team knowledge and coding conventions for autonomous agents?

Yes, you can use markdown files to store team knowledge by writing updated architectural decisions and user preferences into the memory directory, allowing autonomous agents to access and apply consistent coding conventions across tasks.

When should I not use a memory retrieval protocol for agent execution?

A memory retrieval protocol is not needed for agent execution when a task operates in a completely isolated environment with no historical decisions, or when retrieving prior markdown context adds unnecessary latency to stateless operations.